Model · Z.ai · Vision
GLM-OCR
Z.ai's small open OCR model for complex documents — under 1B parameters, built on the GLM-V architecture, and strong on tables, formulas, seals and code-heavy pages. Its SDK adds layout analysis for full document parsing.
- Modality
- Vision
- License
- MIT (Open)
- Parameter size
- 0.9B per the model card (Hugging Face counts 1.3B total weights)
- Released
- January 30, 2026
- Last verified
- October 28, 2026
- Runs locally
- Yes
What you need to run it
- Mac
- Yes. Any Apple Silicon Mac (M1 or newer) with at least 8 GB (16 GB recommended) of memory. Newer chips are faster, but memory is what decides whether it runs.
- Windows / Linux PC
- NVIDIA works best. A graphics card with at least 4 GB (8 GB recommended) of video memory.
- No graphics card
- Not practical. Too slow without a graphics card or Apple Silicon.
Runs on Apple Silicon through mlx-vlm and also in Ollama, so a modest Mac is enough.
Numbers are for: 0.9B model, 16-bit (4-bit MLX builds exist). Our estimate from the model’s size — the maker publishes no figure.
Strengths
- MIT licence for the model — free for commercial use
- Small enough for edge deployment and high-volume services
- Self-reported 94.62 on OmniDocBench v1.5, ranked first overall at release
- Robust on real-world layouts: complex tables, code, seals
- Runs through vLLM, SGLang or Ollama
Weaknesses
- The full pipeline uses PaddlePaddle's PP-DocLayoutV3 (Apache 2.0), so you follow two licences
- Benchmark score is Z.ai's own
- Release date is the Hugging Face repo date; the lab publishes none
Try it
| Where | Type | Notes |
|---|---|---|
| Hugging Face | weights | MIT |
| Ollama | local | Runs on your own machine |
| Z.ai API | hosted-api | API key required |
Official sources
- Model card model
- GitHub github
- Technical report paper
- Z.ai docs docs
Change log
- — Added hardware requirements (Mac support, memory, NVIDIA). Source: estimate from size and community builds (github zai-org/GLM-OCR README (mlx-vlm, Ollama)).
- — Initial entry. Release date is the Hugging Face repo date (2026-01-30); the lab publishes none. Model under MIT, SDK code under Apache 2.0. Added 2026-10-28 from the popularity sweep: 1.75M Hugging Face downloads in the last month, 2.2k likes, 7.5k GitHub stars.
Esc